NetSight
high7.7

CVE-2026-68903

LLMKube is a Kubernetes operator for self-hosted large language model inference across heterogeneous hardware.

Impact

LLMKube is a Kubernetes operator for self-hosted large language model inference across heterogeneous hardware. Prior to 0.9.0, the ModelReconciler accepts arbitrary absolute paths and file:// URIs in Model.spec.source without restricting them to approved roots. A namespace user who can create or update Model and InferenceService resources can cause copyLocalModel to open an attacker-selected file in the controller pod or cause a HostPathVolumeSource to mount an attacker-selected node file when modelCache.enabled is enabled, which is the default. The selected file is copied into model storage and can expose controller service-account credentials or other node secrets outside the attacker's namespace. This issue is fixed in version 0.9.0.

An attacker can exploit this over the network, with a regular user account, without any action by a user. If it succeeds: high risk of data being read. The attack can reach beyond the vulnerable component itself.

Affected packages

EcosystemPackageAffectedFixed in
gogithub.com/defilantech/llmkube<= 0.8.280.9.0

Affected products · Defilantech

ProductAffected versions
LLMKube
before 0.9.0
Version < 0.9.0

Weakness classification

References